© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106124
    Prev
    Next
    INDEX
    Explanations

    Cognitive function

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric strings and digit sequences (e.g. years, IDs, counts, and other numbers).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    refu
    -0.81
    Edm
    -0.80
     kuchni
    -0.78
     fieldNum
    -0.78
    CharCode
    -0.78
    𝑇
    -0.77
     ktorá
    -0.77
    گاب
    -0.77
    eslint
    -0.74
    )}=
    -0.73
    POSITIVE LOGITS
     portal
    1.34
     Portal
    1.08
     NIC
    1.08
     portals
    1.08
    portal
    1.02
    Citizen
    0.85
    NIC
    0.82
    citizen
    0.82
     Saks
    0.82
    rosoft
    0.81
    Activations Density 0.019%

    No Known Activations